Recent Publications
Michael C. Mozer

Computational models in cognitive neuroscience

• Mozer, M. C., & Fan, A. (2007).  Top-down modulation of neural responses in visual perception:  A computational exploration.  Natural Computing. Springer Netherlands.  


• Bohte, S., & Mozer, M. C. (2007).  Reducing the variability of neural responses:  A computational theory of spike-timing dependent plasticity. Neural Computation, 19, 371-403. [short version:  in L. K. Saul, Y. Weiss, & L. Bottou (Eds.), Advances in Neural Information Processing Systems 17 (pp. 201-208).  Cambridge, MA:  MIT Press, 2005.]


• Mozer, M. C., Mytkowicz, T., & Zemel, R. S. (2005).  Stimulus-specific adaptation of neural responses:  Insights from neurophysiology and computational models.  Poster presented at the Cognitive Neuroscience Conference.  New York City, April 2005.  


• Mozer, M. C., Mytkowicz, T., & Zemel, R. S. (2004).  Achieving robust neural representations:  An account of repetition suppression.  Unpublished manuscript.
  

• Mozer, M. C. (2002). Frames of reference in unilateral neglect and spatial attention: A computational perspective. Psychological Review, 109, 156-185.

• Sitton, M., Mozer, M. C., & Farah, M. (2000). Superadditive effects of multiple lesions in a connectionist architecture: Implications for the neuropsychology of optic aphasia, Psychological Review, 107, 709-734.

• O'Reilly, R. C., Mozer, M. C., Munakata, Y., & Miyake, A. (1999). Discrete representations in working memory: A hypothesis and computational investigations. In Proceedings of the Second International Conference on Cognitive Science (pp. 183-188). Tokyo, Japan: Japanese Cognitive Science Society.

• Mozer, M. C., Halligan, P. W., & Marshall, J. C. (1997). The end of the line for a brain-damaged model of unilateral neglect. Cognitive Neuroscience, 9, 171-190.

• Mozer, M. C., & Behrmann, M. (1990).  On the interaction of selective attention and lexical knowledge:  A connectionist account of neglect dyslexia.  Journal of Cognitive Neuroscience, 2, 96-123.

Computational models in cognitive science

• Mozer, M. C., Pashler, H., & Homaei, H. (2008).  Optimal predictions in everyday cognition:  The wisdom of individuals or crowds?  Submitted for publication. 


• Mozer, M. C. (2008).  Attractor networks.  To appear in P. Wilken, A. Cleeremans, & T. Bayne (Eds.), Oxford Companion to Consciousness.  Oxford U. Press.


• Mozer, M. C., & Baldwin, D. S. (2008).  Experience-guided search:  A theory of attentional control.  To appear in J. Platt, D. Koller, & Y. Singer (Eds.), Advances in Neural Information Processing Systems 20.  Cambridge, MA: MIT Press 


• Mozer, M. C., & Wilder, M. (2007).  A unified theory of exogenous and endogenous attentional control.  To appear in Advances in Cognitive Neuroscience (Vol 3). (Poster presented at Cognitive Neuroscience Conference, New York City, May 2007, is also available.) 


• Mozer, M. C., Jones, M., & Shettel, M. (2007).  Context effects in category learning:  An investigation of four probabilistic models.  To appear in Neural Information Processing Systems 19. Cambridge, MA: MIT Press.  


• Mozer, M. C., Kinoshita, S., & Shettel, M. (2007).  Sequential dependencies offer insight into cognitive control.  In W. Gray (Ed.), Integrated Models of Cognitive Systems (pp. 180-193).  Oxford University Press. 


• Baldwin, D., & Mozer, M. C. (2006).  Controlling attention with noise:  The cue-combination model of visual search. In R. Sun & N. Miyake (Eds.), Proceedings of the Twenty  Eighth Annual Conference of the Cognitive Science Society (pp. 42-47).  Hillsdale, NJ:  Erlbaum Associates. 


• Mozer, M. C., Shettel, M., & Vecera, S. P. (2006).  Control of visual attention:  A rational account.  In Y. Weiss, B. Schoelkopf, & J. Platt (Eds.), Neural Information Processing Systems 18 (pp. 923-930).  Cambridge, MA:  MIT Press. 


• Colagrosso, M. D., & Mozer, M. C. (2005).  Theories of access consciousness.  In L. K. Saul, Y. Weiss, & L. Bottou (Eds.), Advances in Neural Information Processing Systems 17 (pp. 289-296).  Cambridge, MA:  MIT Press. 


• Mozer, M. C., Howe, M., & Pashler, H. (2004).  Using testing to enhance learning:  A comparison of two hypotheses.  Proceedings of the Twenty Sixth Annual Conference of the Cognitive Science Society  (pp. 975-980). Hillsdale, NJ: Erlbaum Assoccciates. 

• Mozer, M. C., Kinoshita, S., & Davis, C.  (2004).  Control of response initiation:  Mechanisms of adaptation to recent experience. Proceedings of the Twenty Sixth Annual Conference of the Cognitive Science Society  (pp. 981-986). Hillsdale, NJ: Erlbaum Assoccciates.
  

• Mozer, M. C., Colagrosso, M. D., & Huber, D. E. (2003).   Mechanisms of long-term repetition priming and skill refinement:  A probabilistic pathway model.  In Proceedings of the Twenty Fifth Annual Conference of the Cognitive Science Society. Hillsdale, NJ: Erlbaum Associates. 

• Mozer, M. C., Colagrosso, M. D., & Huber, D. H. (2002). A rational analysis of cognitive control in a speeded discrimination task. In T. Dietterich, S. Becker, & Ghahramani, Z. (Eds.) Advances in Neural Information Processing Systems XIV (pp. 51-57). Cambridge, MA: MIT Press.

• Grimes, D., & Mozer, M. C. (2001). The interplay of symbolic and subsymbolic processes in anagram problem solving. In T. K. Leen, T. Dietterich, & V. Tresp (Eds.), Advances in Neural Information Processing Systems 13 (pp. 17­23). Cambridge, MA: MIT Press. 

• Mozer, M. C. (1999). A principle for unsupervised hierarchical decomposition of visual scenes. In M. S. Kearns, S. A. Solla, & D. Cohn (Eds.), Advances in Neural Information Processing Systems 11 (pp. 52-58). Cambridge, MA: MIT Press.

• Mozer, M. C., & Sitton, M. (1998). Computational modeling of spatial attention. In H. Pashler (Ed.), Attention (pp. 341-393). London: UCL Press.

• Mathis, D., & Mozer, M. C. (1996). Conscious and unconscious perception: A computational theory. In G. Cottrell (Ed.), Proceedings of the Eighteenth Annual Conference of The Cognitive Science Society (pp. 324-328). Hillsdale, NJ: Erlbaum.

• Mathis, D. A., & Mozer, M. C. (1995). On the computational utility of consciousness. In G. Tesauro, D. S. Touretzky, & T. K. Leen (Eds.), Advances in Neural Information Processing Systems 7 (pp. 10-18). Cambridge, MA: MIT Press.

Applications of machine learning

• Richardson, S., Otte, M., Mozer, M. C., Diwan, A., Sweeney, P., Connors, D., & Lacovara, K. (2007).  Discovering the runtime structure of software with probabilistic generative models.


• Hauswirth, M., Diwan, A., Sweeney, P. F., & Mozer, M. C. (2005).  Automated vertical profiling.  In 20th Annual ACM SIGPLAN Conference on Object-Oriented Programming, Systems, Languages, and Applications  (OOPSLA'05).

• Mozer, M. C. (2005).  Lessons from an adaptive house.  In D. Cook & R. Das (Eds.), Smart environments:  Technologies, protocols, and applications (pp. 273-294).  Hoboken, NJ:  J. Wiley & Sons.

•  Pashler, H., Mozer, M. C., & Harris, C. R. (2002). Mating strategies in a Darwinian microworld: Simulating the consequences of female reproductive refractoriness. Adaptive Behavior, 9, 5-15.


• Mozer, M. C., & the Athene Advanced Technology Group. (2000). Prediction and classification. Pittfalls for the unwary.


• Mozer, M. C., Wolniewicz, R., Grimes, D., Johnson, E., & Kaushanksy, H. (2000). Predicting subscriber dissatisfaction and improving retention in the wireless telecommunications industry. IEEE Transactions on Neural Networks, 11, 690-696.


• Mozer, M. C. (1999). An intelligent environment must be adaptive. IEEE Intelligent Systems and their Applications, 14(2) , 11-13.


• Mozer, M. C. (1998). The neural network house: An environment that adapts to its inhabitants. In M. Coen (Ed.), Proceedings of the American Association for Artificial Intelligence Spring Symposium on Intelligent Environments (pp. 110-114). Menlo, Park, CA: AAAI Press.


• Mozer, M. C., Vidmar, L., & Dodier, R. H. (1997). The Neurothermostat: Predictive optimal control of residential heating systems. In M. C. Mozer, M. I. Jordan, & T. Petsche (Eds.), Advances in Neural Information Processing Systems 9 (pp. 953-959). Cambridge, MA: MIT Press.


• Calder, B., Grunwald, D., Jones, M., Lindsay, D., Martin, J., Mozer, M., & Zorn, B. (1997). Evidence-based static branch prediction using machine learning. ACM Transactions on Programming Languages and Systems, 19, 188-222.


• Mozer, M. C. (1996). Neural network speech processing for toys and consumer electronics. IEEE Expert, 11, 4-5.


• Mozer, M. C., & Miller, D. (1998). Parsing the stream of time: The value of event-based segmentation in a complex, real-world control problem. In C. L. Giles & M. Gori (Eds.), Adaptive processing of temporal sequences and data structures (pp. 370–388). Berlin: Springer Verlag. 


• Mozer, M. C., Dodier, R. H., Anderson, M., Vidmar, L., Cruickshank III, R. F., & Miller, D. (1995). The neural network house: An overview. In L. Niklasson & M. Boden (Eds.), Current trends in connectionism (pp. 371-380). Hillsdale, NJ: Erlbaum.


• Dodier, R. H., Lukianow, D., Ries, J., & Mozer, M. C. (1994). A comparison of neural net and conventional techniques for lighting control. Applied Mathematics and Computer Science, 4, 447-462.

Learning algorithms

• Hochreiter, S., & Mozer, M. C. (2007).  Monaural speech separation by support vector machines:  Bridging the divide between supervised and unsupervised learning methods.  To appear in Blind Signal Separation. 


• Yan, L., Dodier, R.,  Mozer, M. C., & Wolniewicz, R. (2003).   Optimizing classifier performance via the Wilcoxon-Mann-Whitney statistic.  In The Proceedings of the International Conference on Machine Learning (ICML) (pp. 848-855). 


• Hochreiter, S., Mozer, M. C., & Obermayer, K. (2003).   Coulomb classifiers:  Generalizing support vector machines via an analogy to electrostatic systems.   In S. Becker, S. Thrun, & K. Obermayer (Eds.), Advances in Neural Information Processing Systems 15 (pp. 545-552). Cambridge, MA: MIT Press. 


• Mozer, M. C., Dodier, R., Colagrosso, M. D., Guerra-Salcedo, C., & Wolniewicz, R. (2002). Prodding the ROC curve: Constrained optimization of classifier performance. In T. Dietterich, S. Becker, & Z. Ghahramani (Eds.), Advances in neural information processing systems XIV (pp. 1409-1415).  Cambridge, MA:  MIT Press. 


• Hochreiter, S., & Mozer, M. C. (2001). Beyond maximum likelihood and density estimation: A sample-based criterion for unsupervised learning of complex models. In T. K. Leen, T. Dietterich, & V. Tresp (Eds.), Advances in Neural Information Processing Systems 13 (pp. 535-541). Cambridge, MA: MIT Press.


• Hochreiter, S., & Mozer, M. C. (2001). Monaural separation and classification of mixed signals: A support-vector regression perspective. Proceedings of the Third International Conference on Independent Component Analysis and Blind Signal Separation, San Diego, CA.


• Mozer, M. C., Zemel, R. S., Behrmann, M., & Williams, C. K. I. (1992). Learning to segment images using dynamic feature binding. Neural Computation, 4, 650-665.


• Mozer, M. C. (1992). Induction of multiscale structure. In J. E. Moody, S. J. Hanson, & R. P. Lippmann (Eds.), Advances in neural information processing systems IV (pp. 275-282). San Mateo, CA: Morgan Kaufmann.


• Mozer, M. C., & Smolensky, P. (1989). Using relevance to reduce network size automatically.  Connection Science, 1, 3-16.

Rule extraction from neural networks

• Alexander, J. A., & Mozer, M. C. (1999). Template-based procedures for neural network interpretation. Neural Networks, 12, 479-498.


• Das, S., & Mozer, M. C. (1998). Dynamic on-line clustering and state extraction: An approach to symbolic learning. Neural Networks, 11, 53-64.


• McMillan, C., Mozer, M. C., & Smolensky, P. (1992). Rule induction through integrated symbolic and subsymbolic processing. In J. E. Moody, S. J. Hanson, & R. P. Lippmann (Eds.), Advances in neural information processing systems 4 (pp. 969-976). San Mateo, CA: Morgan Kaufmann.

Recurrent networks and temporal sequence processing

• Hochreiter, S., & Mozer, M. C. (2001). A discrete probabilistic memory model for discovering dependencies in time. In G. Dorffner, H. Bischof, & K. Hornig (Eds.), Proceedings of the International Conference on Artificial Neural Networks (ICANN). Springer-Verlag.


• Zemel, R. S., & Mozer, M. C. (2001). Localist attractor networks. Neural Computation, 13, 1045-1064.


• Zemel, R. S., Williams, C. K. I., & Mozer, M. C. (1995). Lending direction to neural networks. Neural Networks, 7, 565-579.


• Mozer, M. C. (1994). Neural network music composition by prediction: Exploring the benefits of psychophysical constraints and multiscale processing. Connection Science, 6, 247-280.


• Mozer, M. C. (1993). Neural network architectures for temporal pattern processing. In A. S. Weigend & N. A. Gershenfeld (Eds.), Time series prediction: Forecasting the future and understanding the past (pp. 243-264). Redwood City, CA: Sante Fe Institute Studies in the Sciences of Complexity, Proceedings Volume XVII, Addison-Wesley Publishing.

Experimental psychology

• Pashler, H., Mozer, M. C., Cepeda, N. J., Rohrer, D., & Carpenter, S. K. (Submitted). Does guessing incorrectly impair fact learning?   Submitted for publication.


• Kinoshita, S., Forster, K. I., & Mozer, M. C. (2008). Unconscious cognition isn't that smart: Modulation of masked repetition priming effect in the word naming task.  Cognition. In Press.


• Kinoshita, S., Mozer, M. C., & Forster, K. I. (Submitted).  Modulation of congruence effects with masked primes in the parity decision task.  Submitted for publication.  


• Kinoshita, S., & Mozer, M. C. (2006).  How lexical decision is affected by recent experience:  Symmetric versus asymmetric frequency blocking effects.  Memory and Cognition, 34, 726-742.


• Mozer, M. C., & Vecera, S. P. (2005).  Object- and space-based attention.  In L. Itti, G. Rees, & J. Tsotsos (Eds.), The encyclopedia of the neurobiology of attention (pp. 130-134).  Elsevier Press. 


• Zemel, R. S., Behrmann, M., & Mozer, M. C. (2002). Experience-dependent perceptual grouping and object-based attention.. Journal of Experimental Psychology: Human Perception and Performance, 28, 202-217.


• Behrmann, M., Zemel, R. S., and Mozer, M. C. (1998). Object-based attention and occlusion: Evidence from normal subjects and a computational model. Journal of Experimental Psychology: Human Perception and Performance , 24, 1011-1036.